Classify by ant colony algorithm under the support

Step 2: Building spatial database. We selected 19 correlative data from early research item basic databases as classificatory characters which included DEM, slope, aspect, NDVI, NDBI and 8 texture characters, 6 gray bands to form decision-making table about spatial information. The test integrates multi-source and multi- dimensional spatial data to build spatial database. Step 3 : Classify by ant colony algorithm under the support of different variables and compares their precision see section 4 Step4: Four methods are compared and discussed under the support of 19 variable see section 4

4. COMPARISON AND DISCUSS The classification accuracy refers to the extent of pixels

correctly classified in the remote sensing image classification. The confusion matrix is the relatively common method on the evaluation of remote sensing image classification accuracy. The main parameters of classification accuracy are producer accuracy, user accuracy, overall accuracy, omission errors, commission errors and kappa coefficient. By contrasting the classification results with each other, we choice the best one.

4.1 Classify by ant colony algorithm under the support

of different variables In ant colony algorithm program Dorigo M , Maniezzo V , Colorni A. 1996; Badr A , Fahlny A . 2003 , decision trees are widely used of all machine learning methods. We applied ant colony algorithm to obtain some classification rules from spatial database under the support of different variables. Figure 3 are showed classification result from different variables. We have obtained confusion matrix and accuracy from ENVI. Total accuracy assessments are 89.12 and 90.18 and 92.22 based 8 and 11 and 19 factors. Kappa coefficients are 0.8651 and 0.8781 and0.9034 based 8 and 11 and 19 factors. Figure 4 is comparison of producers accuracy based different factors. Figure 5 is comparison of users accuracy based different factors Figure 3. Classification based on ant colony algorithm under the support of different variables a to c Figure4. Comparison of producers accuracy based different factor Figure5. Comparison of users accuracy based different factors International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XL-2W1, 2013 181

4.2 Rules based on different variable characteristics factors